Luojun Lin

Fuzhou University

Papers

1

Total Citations

51

H-Index

1

About

Luojun Lin is a leading researcher in computer vision and machine learning, with a primary focus on domain adaptation and robust representation learning. His most-cited work, "Self-Supervised Noisy Label Learning for Source-Free Unsupervised Domain Adaptation" (2022, 51 citations), addresses a critical challenge in robot vision: enabling neural networks to adapt to new, unlabeled target domains without access to the original source data or its annotations. This breakthrough tackles the practical constraint of expensive storage, where source data is often unavailable. Lin’s major contribution lies in integrating self-supervised learning to handle noisy labels during adaptation, significantly improving model robustness and generalization. His work has been widely recognized for its impact on real-world applications, such as autonomous systems and robotics, where data privacy and storage limitations are paramount. With over 50 citations on this single paper, Lin’s research continues to influence the development of more efficient, privacy-preserving domain adaptation techniques, making him a notable figure in advancing unsupervised learning under constrained conditions.

Research Focus

Key Achievements

1
H-Index
1
Papers
51
Total Citations
51
Avg Citations/Paper
🏆 Most Cited Paper
Self-Supervised Noisy Label Learning for Source-Free Unsupervised Domain Adaptation
51 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 5
🏛 Institutions: Fuzhou University

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago